Abstract
Gaussian scale mixture models offer a top-down description of signal generation that captures key bottom-up statistical characteristics of filter responses to images. However, the pattern of dependence among the filters for this class of models is prespecified. We propose a novel extension to the gaussian scale mixture model that learns the pattern of dependence from observed inputs and thereby induces a hierarchical representation of these inputs. Specifically, we propose that inputs are generated by gaussian variables (modeling local filter structure), multiplied by a mixer variable that is assigned probabilistically to each input from a set of possible mixers. We demonstrate inference of both components of the generative model, for synthesized data and for different classes of natural images, such as a generic ensemble and faces. For natural images, the mixer variable assignments show invariances resembling those of complex cells in visual cortex; the statistics of the gaussian components of the model are in accord with the outputs of divisive normalization models. We also show how our model helps interrelate a wide range of models of image statistics and cortical processing.
Original language | English (US) |
---|---|
Pages (from-to) | 2680-2718 |
Number of pages | 39 |
Journal | Neural computation |
Volume | 18 |
Issue number | 11 |
DOIs | |
State | Published - Nov 2006 |
ASJC Scopus subject areas
- Arts and Humanities (miscellaneous)
- Cognitive Neuroscience